
# pip install missingno
# pip install catboost
# pip install lightgbm
# pip install plotly


# importing libraries

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import missingno as msno

import warnings
warnings.filterwarnings('ignore')

from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import GradientBoostingClassifier
from xgboost import XGBClassifier
from catboost import CatBoostClassifier
from sklearn.ensemble import ExtraTreesClassifier
from lightgbm import LGBMClassifier
from sklearn.ensemble import VotingClassifier

import folium
from folium.plugins import HeatMap
import plotly.express as px

plt.style.use('fivethirtyeight')
%matplotlib inline
pd.set_option('display.max_columns', 32)


# reading data
df = pd.read_csv('Chicago_Crimes_DataSet/Chicago_Crimes_2012_to_2017.csv')
df.head()


df.describe()


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1456714 entries, 0 to 1456713
Data columns (total 23 columns):
 #   Column                Non-Null Count    Dtype  
---  ------                --------------    -----  
 0   Unnamed: 0            1456714 non-null  int64  
 1   ID                    1456714 non-null  int64  
 2   Case Number           1456713 non-null  object 
 3   Date                  1456714 non-null  object 
 4   Block                 1456714 non-null  object 
 5   IUCR                  1456714 non-null  object 
 6   Primary Type          1456714 non-null  object 
 7   Description           1456714 non-null  object 
 8   Location Description  1455056 non-null  object 
 9   Arrest                1456714 non-null  bool   
 10  Domestic              1456714 non-null  bool   
 11  Beat                  1456714 non-null  int64  
 12  District              1456713 non-null  float64
 13  Ward                  1456700 non-null  float64
 14  Community Area        1456674 non-null  float64
 15  FBI Code              1456714 non-null  object 
 16  X Coordinate          1419631 non-null  float64
 17  Y Coordinate          1419631 non-null  float64
 18  Year                  1456714 non-null  int64  
 19  Updated On            1456714 non-null  object 
 20  Latitude              1419631 non-null  float64
 21  Longitude             1419631 non-null  float64
 22  Location              1419631 non-null  object 
dtypes: bool(2), float64(7), int64(4), object(10)
memory usage: 236.2+ MB


# checking for null values 

null = pd.DataFrame({'Null Values' : df.isna().sum(), 'Percentage Null Values' : (df.isna().sum()) / (df.shape[0]) * (100)})
null


# filling null values with zero

df.fillna(0, inplace = True)


# visualizing null values
msno.bar(df)
plt.show()


# # adults, babies and children cant be zero at same time, so dropping the rows having all these zero at same time
# filter = (df.children == 0) & (df.adults == 0) & (df.babies == 0)
# df[filter]

# df = df[~filter]
df


# 根据犯罪类型和年份分组统计数量
grouped = df.groupby(['Year','Primary Type']).size()

# 计算每个犯罪类型在每个年份的比例
grouped_pct = grouped.groupby(level=1).apply(lambda x: 100 * x / float(x.sum()))

# 绘制百分比堆积柱状图
fig, ax = plt.subplots(figsize=(20, 10))
grouped_pct.unstack().plot(kind='bar', stacked=True, ax=ax)

# 设置图表属性
ax.set_xlabel('Year')
ax.set_ylabel('Percentage of Crimes')
ax.set_title('Crime Types Over the Years')

# 显示图表
plt.show()


import pandas as pd
import geopandas as gpd
import matplotlib.pyplot as plt

df1=df

# 加载GeoJSON文件
chicago = gpd.read_file('Chicago_Crimes_DataSet/chicago_community_areas.geojson')

# 匹配GeoJSON中的area_numbe与CSV中的Community Area
df1['area_numbe'] = df['Community Area'].astype(int).astype(str)
df1 = df.merge(chicago, on='area_numbe')

# 计算每个Community Area的犯罪事件总数
crime_count = df.groupby('area_numbe').size().reset_index(name='crime_count')

# 将结果与GeoJSON合并，并呈现在地图上
chicago = chicago.merge(crime_count, on='area_numbe')
ax = chicago.plot(column='crime_count', cmap='OrRd', legend=True, figsize=(15, 15))

# 添加每个区域的标签
for idx, row in chicago.iterrows():
    plt.annotate(text=row['crime_count'], xy=row['geometry'].centroid.coords[0], horizontalalignment='center')

# 显示地图
plt.axis('off')
plt.show()


import pandas as pd
import geopandas as gpd

# 加载数据集
df2 = df

# 匹配GeoJSON中的area_numbe与CSV中的Community Area
chicago = gpd.read_file('Chicago_Crimes_DataSet/chicago_community_areas.geojson')
df2['area_numbe'] = df['Community Area'].astype(int).astype(str)
df2 = df2.merge(chicago, on='area_numbe')

# 计算每个Community Area的犯罪事件总数和涉及家暴的事件总数
crime_count = df2.groupby('area_numbe').size().reset_index(name='crime_count')
domestic_count = df2.loc[df['Domestic'] == True].groupby('area_numbe').size().reset_index(name='domestic_count')

# 将结果与GeoJSON合并，并计算家暴犯罪占比
chicago = chicago.merge(crime_count, on='area_numbe')
chicago = chicago.merge(domestic_count, on='area_numbe', how='left').fillna(0)
chicago['domestic_ratio'] = chicago['domestic_count'] / chicago['crime_count'] * 100

# 排序并打印前三个区
top_3 = chicago[['community', 'domestic_ratio']].sort_values('domestic_ratio', ascending=False).head(3)
print(top_3)

# 在地图上呈现
ax = chicago.plot(column='crime_count', cmap='OrRd', legend=True, figsize=(15, 15))
ax.set_title("Percentage of Domestic Related Crimes by Community Area in Chicago")
ax.set_axis_off()

for idx, row in chicago.iterrows():
    ax.annotate(text=str(int(row['domestic_ratio'])) + '%', xy=row['geometry'].centroid.coords[0], 
                horizontalalignment='center', verticalalignment='center')

      community  domestic_ratio
11  FOREST GLEN       18.088871
60    GAGE PARK       17.846542
15  IRVING PARK       17.439658


import pandas as pd
import matplotlib.pyplot as plt

# Load the dataset
df3 = df

# Convert the Date column to datetime format
df3['Date'] = pd.to_datetime(df3['Date'])

# Extract the day of the week from the Date column
df3['DayOfWeek'] = df3['Date'].dt.day_name()

# Group the crimes by day of the week and count the number of crimes on each day
crimes_by_day = df3.groupby('DayOfWeek')['ID'].count()

# Set the figure size
fig, ax = plt.subplots(figsize=(10, 10))

# Plot a pie chart of the distribution
ax.pie(crimes_by_day, labels=crimes_by_day.index, autopct='%1.1f%%')
ax.set_title('Distribution of Crimes by Day of the Week')

# Show the plot
plt.show()

# Print the percentage of crimes on each day
print('Crimes by Day of the Week:\n', crimes_by_day)

Crimes by Day of the Week:
 DayOfWeek
Friday       218643
Monday       205762
Saturday     209743
Sunday       202212
Thursday     205851
Tuesday      206129
Wednesday    208374
Name: ID, dtype: int64


import pandas as pd
import plotly.express as px

# Load the dataset
df4 = pd.read_csv('Chicago_Crimes_DataSet/Chicago_Crimes_2012_to_2017.csv')

# Count the number of crimes by location description
crime_counts = df4['Location Description'].value_counts()

# Create a dataframe with the location descriptions and counts
crime_df = pd.DataFrame({'Location Description': crime_counts.index, 'Count': crime_counts.values})

# Calculate the percentage of crimes in each location
crime_df['Percentage'] = crime_df['Count'] / sum(crime_df['Count']) * 100

# Create the Treemap figure
fig = px.treemap(crime_df, path=['Location Description'], values='Count', color='Percentage',height=700,
                 color_continuous_scale='spectral', labels={'Count': 'Number of Crimes', 'Percentage': 'Percentage of Total Crimes'})

# Update the text position and font size
fig.update_traces(textposition='middle center', textfont=dict(size=10), texttemplate='%{value}<br>%{label}')

# Show the figure
fig.show()


# Sort the dataframe by percentage in descending order
crime_df = crime_df.sort_values(by='Percentage', ascending=False)

# Select only the top five rows
top_five = crime_df[['Location Description', 'Percentage']].head(5)

# Print the top five locations by percentage
print(top_five.to_string(index=False))

Location Description  Percentage
              STREET   22.711909
           RESIDENCE   16.049554
           APARTMENT   12.715868
            SIDEWALK   11.057375
               OTHER    3.833117


df = pd.read_csv('Chicago_Crimes_DataSet/Chicago_Crimes_2012_to_2017.csv')
null = pd.DataFrame({'Null Values' : df.isna().sum(), 'Percentage Null Values' : (df.isna().sum()) / (df.shape[0]) * (100)})
df.fillna(0, inplace = True)
# Merge Crime Dataset with Economy DataSet

# get the economy data
poverty = pd.read_excel('Chicago_Economy_DataSet/poverty.xlsx')
median_house_income = pd.read_excel('Chicago_Economy_DataSet/median_house_income.xlsx')
black = pd.read_excel('Chicago_Economy_DataSet/black.xlsx')
naturecitizenship = pd.read_excel('Chicago_Economy_DataSet/citizenship.xlsx')
education = pd.read_excel('Chicago_Economy_DataSet/education.xlsx')
health_insurance = pd.read_excel('Chicago_Economy_DataSet/health_insurance.xlsx')
hispanic_latino = pd.read_excel('Chicago_Economy_DataSet/hispanic_latino.xlsx')
noncitizenship = pd.read_excel('Chicago_Economy_DataSet/noncitizenship.xlsx')
owner_occupied = pd.read_excel('Chicago_Economy_DataSet/owner_occupied.xlsx')

merged = pd.merge(df, poverty, on='Community Area')
merged1 = pd.merge(df, median_house_income, on='Community Area')
merged2 = pd.merge(df, black, on='Community Area')
merged3 = pd.merge(df, naturecitizenship, on='Community Area')
merged4 = pd.merge(df, health_insurance, on='Community Area')
merged5 = pd.merge(df, hispanic_latino, on='Community Area')
merged6 = pd.merge(df, noncitizenship, on='Community Area')
merged7 = pd.merge(df, owner_occupied, on='Community Area')
merged8 = pd.merge(df, education, on='Community Area')

df1 = merged
df1['poverty'] = merged.lookup(merged.index,merged['Year'])
df1['median_house_income'] = merged1.lookup(merged1.index,merged1['Year'])
df1['black'] = merged2.lookup(merged2.index,merged2['Year'])
df1['naturecitizenship'] = merged3.lookup(merged3.index,merged3['Year'])
df1['health_insurance'] = merged4.lookup(merged4.index,merged4['Year'])
df1['hispanic_latino'] = merged5.lookup(merged5.index,merged5['Year'])
df1['noncitizenship'] = merged6.lookup(merged6.index,merged6['Year'])
df1['owner_occupied'] = merged7.lookup(merged7.index,merged7['Year'])
df1['education'] = merged8.lookup(merged8.index,merged8['Year'])

df1.to_csv('test.csv')
data = pd.read_csv('test.csv')
data = data.drop(columns =['2012','2013','2014','2015','2016','2017','IUCR',"Description"],axis=1)


from sklearn.preprocessing import LabelEncoder

object_features = ["Case Number", "Date", "Block", "Primary Type", 
                    "Location Description", "FBI Code",
                    "Updated On", "Location"]
for feature in object_features:
    data[feature]=LabelEncoder().fit_transform(data[feature])
    
data.head()


plt.figure(figsize = (36, 20))

corr = data.corr()
sns.heatmap(corr, annot = True, linewidths = 1)
plt.show()


correlation = data.corr()['Primary Type'].abs().sort_values(ascending = False)
correlation

Primary Type            1.000000
Domestic                0.266836
education               0.143164
median_house_income     0.139249
Location Description    0.112288
poverty                 0.101108
black                   0.094331
Block                   0.082833
health_insurance        0.080434
Community Area          0.070855
Location                0.070278
Ward                    0.062362
naturecitizenship       0.046366
FBI Code                0.039151
Beat                    0.032409
District                0.032054
noncitizenship          0.031606
hispanic_latino         0.018144
Year                    0.012897
Y Coordinate            0.010279
Arrest                  0.010178
Updated On              0.010095
owner_occupied          0.009675
Case Number             0.009325
Unnamed: 0.1            0.009299
Date                    0.008076
Unnamed: 0              0.003608
Latitude                0.003370
X Coordinate            0.002514
Longitude               0.002374
ID                      0.000722
Name: Primary Type, dtype: float64


# dropping columns that are not useful(which is low than 0.01)

useless_col = ['owner_occupied','Case Number','Unnamed: 0.1', 'Date', 'Unnamed: 0', 'Longitude','X Coordinate', 'ID','Latitude']

data.drop(useless_col, axis = 1, inplace = True)


data.var()

Block                   9.398763e+07
Primary Type            1.411251e+02
Location Description    1.675417e+03
Arrest                  1.919809e-01
Domestic                1.282452e-01
Beat                    4.783784e+05
District                4.767494e+01
Ward                    1.906043e+02
Community Area          4.596774e+02
FBI Code                4.222913e+01
Y Coordinate            8.930387e+10
Year                    2.101281e+00
Updated On              5.181823e+04
Location                1.043733e+10
poverty                 1.296835e-02
median_house_income     5.766074e+08
black                   1.564294e-01
naturecitizenship       3.495513e-03
health_insurance        4.472351e-03
hispanic_latino         6.618987e-02
noncitizenship          7.383363e-03
education               5.702499e-02
dtype: float64


# normalizing numerical variables

from sklearn.preprocessing import MinMaxScaler

# create a scaler object
scaler = MinMaxScaler()

# select the columns to be scaled
cols_to_scale = ['Block', 'Location Description', 'Beat', 'District', 'Ward', 
                 'Community Area', 'FBI Code', 'Y Coordinate','Updated On', 
                 'Year', 'Location','poverty',	'median_house_income',	'black',
                 'naturecitizenship'	,'health_insurance'	,'hispanic_latino',
                 'noncitizenship',	'education']

for feature in cols_to_scale:
    data[feature] = data[feature].replace(to_replace="NaN", value=np.NaN)
    data[feature] = data[feature].fillna(data[feature].median(skipna=True))

# fit and transform the selected columns using the scaler object
data[cols_to_scale] = scaler.fit_transform(data[cols_to_scale])

# print the normalized dataframe
data


data.var()

Block                     0.087613
Primary Type            141.125095
Location Description      0.083090
Arrest                    0.191981
Domestic                  0.128245
Beat                      0.081415
District                  0.049610
Ward                      0.076242
Community Area            0.079584
FBI Code                  0.067567
Y Coordinate              0.023448
Year                      0.084051
Updated On                0.056461
Location                  0.076956
poverty                   0.031454
median_house_income       0.046150
black                     0.156956
naturecitizenship         0.031889
health_insurance          0.042082
hispanic_latino           0.077165
noncitizenship            0.057027
education                 0.088393
dtype: float64


y = data ['Primary Type']
X = data.drop(['Primary Type'], axis=1)
X.shape,y.shape

((1456661, 21), (1456661,))


# splitting data into training set and test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25)


# Fit the logistic regression model
lr = LogisticRegression()
lr.fit(X_train, y_train)

# Make predictions and evaluate the model
y_pred_lr = lr.predict(X_test)
acc_lr = accuracy_score(y_test, y_pred_lr)
conf = confusion_matrix(y_test, y_pred_lr)
clf_report = classification_report(y_test, y_pred_lr)

print(f"Accuracy Score of Logistic Regression is : {acc_lr}")
print(f"Confusion Matrix : \n{conf}")
print(f"Classification Report : \n{clf_report}")

Accuracy Score of Logistic Regression is : 0.7030969393078981
Confusion Matrix : 
[[    0     0   463 ...     0     0     0]
 [    0   142 11683 ...     0  8111     0]
 [    0    21 54157 ...     0  9860     0]
 ...
 [    0     0   110 ...     0    56     0]
 [    0     8  2887 ...     0 78180     0]
 [    0     0     0 ...     0     0     6]]
Classification Report : 
              precision    recall  f1-score   support

           0       0.00      0.00      0.00       559
           1       0.70      0.01      0.01     22870
           2       0.74      0.82      0.78     66144
           3       0.54      0.24      0.34     21149
           4       0.00      0.00      0.00        10
           5       0.00      0.00      0.00      1748
           6       0.83      0.93      0.88     38801
           7       0.56      0.55      0.55      9173
           8       0.89      0.60      0.72     18869
           9       0.00      0.00      0.00       544
          10       0.00      0.00      0.00       661
          11       0.00      0.00      0.00         7
          12       0.00      0.00      0.00      1556
          13       0.00      0.00      0.00       164
          14       0.00      0.00      0.00       272
          15       0.00      0.00      0.00       491
          16       0.06      0.00      0.00     15240
          17       0.73      0.96      0.83     33789
          18       0.00      0.00      0.00         7
          19       0.00      0.00      0.00        26
          21       0.00      0.00      0.00        57
          22       0.92      0.21      0.34      2803
          23       0.00      0.00      0.00         7
          24       0.75      0.90      0.82     21830
          25       0.00      0.00      0.00      1880
          26       0.00      0.00      0.00        14
          27       0.08      0.00      0.00      3261
          28       0.76      0.90      0.82     14425
          29       0.00      0.00      0.00      1255
          30       0.00      0.00      0.00       198
          31       0.62      0.95      0.75     82055
          32       0.02      0.00      0.00      4301

    accuracy                           0.70    364166
   macro avg       0.26      0.22      0.21    364166
weighted avg       0.65      0.70      0.64    364166


knn = KNeighborsClassifier()
knn.fit(X_train, y_train)

y_pred_knn = knn.predict(X_test)

acc_knn = accuracy_score(y_test, y_pred_knn)
conf = confusion_matrix(y_test, y_pred_knn)
clf_report = classification_report(y_test, y_pred_knn)

print(f"Accuracy Score of KNN is : {acc_knn}")
print(f"Confusion Matrix : \n{conf}")
print(f"Classification Report : \n{clf_report}")

Accuracy Score of KNN is : 0.8188463502908014
Confusion Matrix : 
[[   26    25   456 ...     0     8     0]
 [    7 10645  7980 ...     1  1798     0]
 [   31  3872 57851 ...     0  2168     1]
 ...
 [    0    75    75 ...     0    12     0]
 [    1  1267  1591 ...     0 75682     0]
 [    0     0    10 ...     0     0  2224]]
Classification Report : 
              precision    recall  f1-score   support

           0       0.29      0.05      0.08       559
           1       0.58      0.47      0.52     22870
           2       0.80      0.87      0.84     66144
           3       0.77      0.77      0.77     21149
           4       0.22      0.20      0.21        10
           5       0.46      0.13      0.20      1748
           6       0.92      0.94      0.93     38801
           7       0.60      0.60      0.60      9173
           8       0.92      0.84      0.88     18869
           9       0.93      0.41      0.57       544
          10       0.94      0.37      0.53       661
          11       0.00      0.00      0.00         7
          12       0.35      0.24      0.29      1556
          13       0.00      0.00      0.00       164
          14       0.43      0.04      0.07       272
          15       0.52      0.23      0.32       491
          16       0.82      0.68      0.74     15240
          17       0.92      0.97      0.94     33789
          18       0.00      0.00      0.00         7
          19       0.00      0.00      0.00        26
          21       0.00      0.00      0.00        57
          22       0.54      0.19      0.28      2803
          23       0.00      0.00      0.00         7
          24       0.73      0.86      0.79     21830
          25       0.88      0.85      0.86      1880
          26       0.00      0.00      0.00        14
          27       0.53      0.33      0.41      3261
          28       0.82      0.79      0.80     14425
          29       0.62      0.10      0.17      1255
          30       0.00      0.00      0.00       198
          31       0.86      0.92      0.89     82055
          32       0.72      0.52      0.60      4301

    accuracy                           0.82    364166
   macro avg       0.51      0.39      0.42    364166
weighted avg       0.81      0.82      0.81    364166


dtc = DecisionTreeClassifier()
dtc.fit(X_train, y_train)

y_pred_dtc = dtc.predict(X_test)

acc_dtc = accuracy_score(y_test, y_pred_dtc)
conf = confusion_matrix(y_test, y_pred_dtc)
clf_report = classification_report(y_test, y_pred_dtc)

print(f"Accuracy Score of Decision Tree is : {acc_dtc}")
print(f"Confusion Matrix : \n{conf}")
print(f"Classification Report : \n{clf_report}")

Accuracy Score of Decision Tree is : 0.964812750229291
Confusion Matrix : 
[[  557     0     0 ...     0     0     0]
 [    0 22647     0 ...   223     0     0]
 [    0     0 66144 ...     0     0     0]
 ...
 [    0   161     0 ...    10     0     0]
 [    0     0     0 ...     0 82055     0]
 [    0     0     0 ...     0     0  4261]]
Classification Report : 
              precision    recall  f1-score   support

           0       0.99      1.00      0.99       559
           1       0.99      0.99      0.99     22870
           2       1.00      1.00      1.00     66144
           3       1.00      1.00      1.00     21149
           4       0.07      0.30      0.11        10
           5       0.93      0.92      0.93      1748
           6       1.00      1.00      1.00     38801
           7       0.64      0.66      0.65      9173
           8       1.00      1.00      1.00     18869
           9       1.00      0.99      1.00       544
          10       1.00      1.00      1.00       661
          11       0.00      0.00      0.00         7
          12       0.44      0.44      0.44      1556
          13       0.04      0.04      0.04       164
          14       0.28      0.29      0.29       272
          15       1.00      1.00      1.00       491
          16       1.00      1.00      1.00     15240
          17       0.98      0.98      0.98     33789
          18       0.00      0.00      0.00         7
          19       0.00      0.00      0.00        26
          21       0.19      0.21      0.20        57
          22       0.60      0.65      0.63      2803
          23       0.00      0.00      0.00         7
          24       0.81      0.79      0.80     21830
          25       1.00      1.00      1.00      1880
          26       0.00      0.00      0.00        14
          27       0.61      0.60      0.60      3261
          28       1.00      1.00      1.00     14425
          29       0.87      0.83      0.85      1255
          30       0.04      0.05      0.04       198
          31       1.00      1.00      1.00     82055
          32       1.00      0.99      0.99      4301

    accuracy                           0.96    364166
   macro avg       0.64      0.65      0.64    364166
weighted avg       0.97      0.96      0.97    364166


rd_clf = RandomForestClassifier()
rd_clf.fit(X_train, y_train)

y_pred_rd_clf = rd_clf.predict(X_test)

acc_rd_clf = accuracy_score(y_test, y_pred_rd_clf)
conf = confusion_matrix(y_test, y_pred_rd_clf)
clf_report = classification_report(y_test, y_pred_rd_clf)

print(f"Accuracy Score of Random Forest is : {acc_rd_clf}")
print(f"Confusion Matrix : \n{conf}")
print(f"Classification Report : \n{clf_report}")

Accuracy Score of Random Forest is : 0.9667459345463333
Confusion Matrix : 
[[  428     0    94 ...     0     0     0]
 [    0 22792    39 ...    10     1     0]
 [    0    33 66094 ...     0     5     0]
 ...
 [    0   169     0 ...     2     0     0]
 [    0     0     6 ...     0 82049     0]
 [    0     0     0 ...     0     0  4181]]
Classification Report : 
              precision    recall  f1-score   support

           0       0.99      0.77      0.86       559
           1       0.98      1.00      0.99     22870
           2       1.00      1.00      1.00     66144
           3       1.00      1.00      1.00     21149
           4       0.25      0.20      0.22        10
           5       0.89      0.73      0.80      1748
           6       0.99      1.00      1.00     38801
           7       0.74      0.67      0.70      9173
           8       1.00      1.00      1.00     18869
           9       0.96      0.94      0.95       544
          10       0.98      0.81      0.89       661
          11       0.00      0.00      0.00         7
          12       0.49      0.43      0.46      1556
          13       0.17      0.04      0.07       164
          14       0.33      0.11      0.16       272
          15       0.90      0.78      0.83       491
          16       1.00      1.00      1.00     15240
          17       0.98      0.98      0.98     33789
          18       0.00      0.00      0.00         7
          19       0.33      0.04      0.07        26
          21       0.33      0.05      0.09        57
          22       0.77      0.58      0.66      2803
          23       0.00      0.00      0.00         7
          24       0.81      0.89      0.85     21830
          25       0.98      0.97      0.97      1880
          26       0.00      0.00      0.00        14
          27       0.64      0.59      0.62      3261
          28       0.98      0.99      0.98     14425
          29       0.81      0.70      0.75      1255
          30       0.11      0.01      0.02       198
          31       1.00      1.00      1.00     82055
          32       0.96      0.97      0.97      4301

    accuracy                           0.97    364166
   macro avg       0.67      0.60      0.62    364166
weighted avg       0.97      0.97      0.97    364166


ada = AdaBoostClassifier(base_estimator = dtc)
ada.fit(X_train, y_train)

y_pred_ada = ada.predict(X_test)

acc_ada = accuracy_score(y_test, y_pred_ada)
conf = confusion_matrix(y_test, y_pred_ada)
clf_report = classification_report(y_test, y_pred_ada)

print(f"Accuracy Score of Ada Boost Classifier is : {acc_ada}")
print(f"Confusion Matrix : \n{conf}")
print(f"Classification Report : \n{clf_report}")

Accuracy Score of Ada Boost Classifier is : 0.971883701388927
Confusion Matrix : 
[[  557     0     0 ...     0     0     0]
 [    0 22857     0 ...    13     0     0]
 [    0     0 66144 ...     0     0     0]
 ...
 [    0   169     0 ...     2     0     0]
 [    0     0     0 ...     0 82055     0]
 [    0     0     0 ...     0     0  4295]]
Classification Report : 
              precision    recall  f1-score   support

           0       1.00      1.00      1.00       559
           1       0.99      1.00      1.00     22870
           2       1.00      1.00      1.00     66144
           3       1.00      1.00      1.00     21149
           4       0.33      0.30      0.32        10
           5       0.92      0.98      0.95      1748
           6       1.00      1.00      1.00     38801
           7       0.72      0.65      0.68      9173
           8       1.00      1.00      1.00     18869
           9       1.00      0.99      1.00       544
          10       1.00      1.00      1.00       661
          11       0.00      0.00      0.00         7
          12       0.49      0.43      0.46      1556
          13       0.15      0.05      0.07       164
          14       0.52      0.25      0.34       272
          15       1.00      1.00      1.00       491
          16       1.00      1.00      1.00     15240
          17       0.99      0.98      0.98     33789
          18       0.00      0.00      0.00         7
          19       0.25      0.04      0.07        26
          21       0.33      0.12      0.18        57
          22       0.80      0.63      0.71      2803
          23       0.00      0.00      0.00         7
          24       0.81      0.89      0.85     21830
          25       1.00      1.00      1.00      1880
          26       0.00      0.00      0.00        14
          27       0.67      0.65      0.66      3261
          28       1.00      1.00      1.00     14425
          29       0.86      0.95      0.90      1255
          30       0.09      0.01      0.02       198
          31       1.00      1.00      1.00     82055
          32       1.00      1.00      1.00      4301

    accuracy                           0.97    364166
   macro avg       0.69      0.65      0.66    364166
weighted avg       0.97      0.97      0.97    364166


gb = GradientBoostingClassifier()
gb.fit(X_train, y_train)

y_pred_gb = gb.predict(X_test)

acc_gb = accuracy_score(y_test, y_pred_gb)
conf = confusion_matrix(y_test, y_pred_gb)
clf_report = classification_report(y_test, y_pred_gb)

print(f"Accuracy Score of Ada Boost Classifier is : {acc_gb}")
print(f"Confusion Matrix : \n{conf}")
print(f"Classification Report : \n{clf_report}")

Accuracy Score of Ada Boost Classifier is : 0.9123970936331234
Confusion Matrix : 
[[  534     0     4 ...     0     0     0]
 [   15 22126   483 ...     2    21     0]
 [   52   255 64627 ...    11    40     0]
 ...
 [    0   153    11 ...     0     0     0]
 [   38   726  2733 ...     0 77798     0]
 [    1     9     2 ...     0     0  4205]]
Classification Report : 
              precision    recall  f1-score   support

           0       0.62      0.96      0.75       559
           1       0.91      0.97      0.94     22870
           2       0.93      0.98      0.95     66144
           3       1.00      0.95      0.97     21149
           4       0.02      0.10      0.03        10
           5       0.00      0.00      0.00      1748
           6       1.00      0.95      0.97     38801
           7       0.68      0.56      0.61      9173
           8       0.99      0.94      0.97     18869
           9       1.00      0.70      0.83       544
          10       0.00      0.00      0.00       661
          11       0.00      0.14      0.00         7
          12       0.00      0.00      0.00      1556
          13       0.01      0.01      0.01       164
          14       0.01      0.01      0.01       272
          15       1.00      0.42      0.60       491
          16       1.00      0.95      0.98     15240
          17       0.99      0.92      0.95     33789
          18       0.00      0.00      0.00         7
          19       0.00      0.00      0.00        26
          20       0.00      0.00      0.00         0
          21       0.01      0.14      0.01        57
          22       0.07      0.06      0.06      2803
          23       0.00      0.29      0.00         7
          24       0.68      0.87      0.77     21830
          25       1.00      0.98      0.99      1880
          26       0.00      0.00      0.00        14
          27       0.59      0.49      0.54      3261
          28       0.97      0.97      0.97     14425
          29       0.81      0.24      0.37      1255
          30       0.00      0.00      0.00       198
          31       1.00      0.95      0.97     82055
          32       1.00      0.98      0.99      4301

    accuracy                           0.91    364166
   macro avg       0.49      0.47      0.46    364166
weighted avg       0.93      0.91      0.92    364166


xgb = XGBClassifier(booster = 'gbtree', learning_rate = 0.1, max_depth = 5, n_estimators = 180)
xgb.fit(X_train, y_train)

y_pred_xgb = xgb.predict(X_test)

acc_xgb = accuracy_score(y_test, y_pred_xgb)
conf = confusion_matrix(y_test, y_pred_xgb)
clf_report = classification_report(y_test, y_pred_xgb)

print(f"Accuracy Score of Ada Boost Classifier is : {acc_xgb}")
print(f"Confusion Matrix : \n{conf}")
print(f"Classification Report : \n{clf_report}")

Accuracy Score of Ada Boost Classifier is : 0.9756869120126536
Confusion Matrix : 
[[  557     0     0 ...     0     0     0]
 [    0 22870     0 ...     0     0     0]
 [    0     0 66144 ...     0     0     0]
 ...
 [    0   170     0 ...     0     0     0]
 [    0     0     0 ...     0 82055     0]
 [    0     0     0 ...     0     0  4299]]
Classification Report : 
              precision    recall  f1-score   support

           0       1.00      1.00      1.00       559
           1       0.99      1.00      1.00     22870
           2       1.00      1.00      1.00     66144
           3       1.00      1.00      1.00     21149
           4       0.50      0.20      0.29        10
           5       0.92      1.00      0.96      1748
           6       1.00      1.00      1.00     38801
           7       0.78      0.69      0.73      9173
           8       1.00      1.00      1.00     18869
           9       1.00      1.00      1.00       544
          10       1.00      1.00      1.00       661
          11       0.00      0.00      0.00         7
          12       0.60      0.37      0.46      1556
          13       0.00      0.00      0.00       164
          14       0.78      0.29      0.42       272
          15       1.00      1.00      1.00       491
          16       1.00      1.00      1.00     15240
          17       0.99      0.97      0.98     33789
          18       0.00      0.00      0.00         7
          19       0.00      0.00      0.00        26
          21       0.67      0.11      0.18        57
          22       0.97      0.58      0.73      2803
          23       0.00      0.00      0.00         7
          24       0.81      0.94      0.87     21830
          25       1.00      1.00      1.00      1880
          26       0.00      0.00      0.00        14
          27       0.72      0.73      0.72      3261
          28       1.00      1.00      1.00     14425
          29       0.85      0.99      0.92      1255
          30       0.00      0.00      0.00       198
          31       1.00      1.00      1.00     82055
          32       1.00      1.00      1.00      4301

    accuracy                           0.98    364166
   macro avg       0.71      0.65      0.66    364166
weighted avg       0.97      0.98      0.97    364166


cat = CatBoostClassifier(iterations=100)
cat.fit(X_train, y_train)

y_pred_cat = cat.predict(X_test)

acc_cat = accuracy_score(y_test, y_pred_cat)
conf = confusion_matrix(y_test, y_pred_cat)
clf_report = classification_report(y_test, y_pred_cat)

Learning rate set to 0.5
0:	learn: 1.0014762	total: 3.52s	remaining: 5m 48s
1:	learn: 4.4842977	total: 6.12s	remaining: 4m 59s
2:	learn: 448.0797461	total: 8.79s	remaining: 4m 44s
3:	learn: 1828.4033638	total: 11.6s	remaining: 4m 38s
4:	learn: 2163.4590209	total: 14.5s	remaining: 4m 36s
5:	learn: 543.8278404	total: 17.4s	remaining: 4m 32s
6:	learn: 499.4815133	total: 20.1s	remaining: 4m 27s
7:	learn: 463.3452341	total: 22.7s	remaining: 4m 21s
8:	learn: 400.1935794	total: 25.3s	remaining: 4m 15s
9:	learn: 301.2618592	total: 28.2s	remaining: 4m 13s
10:	learn: 328.7573425	total: 31.1s	remaining: 4m 11s
11:	learn: 326.7148245	total: 34s	remaining: 4m 9s
12:	learn: 284.7939720	total: 36.7s	remaining: 4m 5s
13:	learn: 246.2083953	total: 39.4s	remaining: 4m 1s
14:	learn: 218.5380871	total: 42.1s	remaining: 3m 58s
15:	learn: 302.4180072	total: 45.1s	remaining: 3m 56s
16:	learn: 283.4308847	total: 48s	remaining: 3m 54s
17:	learn: 257.6146268	total: 50.7s	remaining: 3m 51s
18:	learn: 227.9043492	total: 53.5s	remaining: 3m 47s
19:	learn: 202.3874307	total: 56.2s	remaining: 3m 44s
20:	learn: 179.9474287	total: 58.9s	remaining: 3m 41s
21:	learn: 166.1768008	total: 1m 1s	remaining: 3m 39s
22:	learn: 181.7092653	total: 1m 4s	remaining: 3m 36s
23:	learn: 175.9586111	total: 1m 7s	remaining: 3m 34s
24:	learn: 181.8385216	total: 1m 10s	remaining: 3m 30s
25:	learn: 197.7681567	total: 1m 12s	remaining: 3m 27s
26:	learn: 179.3972472	total: 1m 15s	remaining: 3m 25s
27:	learn: 181.3368717	total: 1m 18s	remaining: 3m 22s
28:	learn: 156.8037334	total: 1m 21s	remaining: 3m 19s
29:	learn: 167.9806554	total: 1m 24s	remaining: 3m 17s
30:	learn: 190.2180226	total: 1m 27s	remaining: 3m 13s
31:	learn: 170.0498274	total: 1m 29s	remaining: 3m 10s
32:	learn: 157.5070215	total: 1m 32s	remaining: 3m 8s
33:	learn: 131.8342794	total: 1m 35s	remaining: 3m 5s
34:	learn: 140.5608261	total: 1m 38s	remaining: 3m 2s
35:	learn: 192.4880355	total: 1m 41s	remaining: 2m 59s
36:	learn: 171.0917027	total: 1m 43s	remaining: 2m 56s
37:	learn: 154.3120471	total: 1m 46s	remaining: 2m 53s
38:	learn: 128.7470442	total: 1m 49s	remaining: 2m 51s
39:	learn: 137.1303710	total: 1m 52s	remaining: 2m 48s
40:	learn: 177.3932408	total: 1m 55s	remaining: 2m 46s
41:	learn: 149.9230529	total: 1m 58s	remaining: 2m 43s
42:	learn: 132.0465373	total: 2m	remaining: 2m 39s
43:	learn: 125.7449745	total: 2m 3s	remaining: 2m 37s
44:	learn: 123.7508094	total: 2m 6s	remaining: 2m 34s
45:	learn: 132.0295684	total: 2m 9s	remaining: 2m 31s
46:	learn: 109.3483204	total: 2m 12s	remaining: 2m 29s
47:	learn: 148.9888131	total: 2m 14s	remaining: 2m 26s
48:	learn: 166.3803982	total: 2m 17s	remaining: 2m 23s
49:	learn: 137.9084915	total: 2m 20s	remaining: 2m 20s
50:	learn: 130.6854619	total: 2m 23s	remaining: 2m 17s
51:	learn: 122.1500752	total: 2m 26s	remaining: 2m 15s
52:	learn: 143.8020903	total: 2m 29s	remaining: 2m 12s
53:	learn: 154.0074006	total: 2m 31s	remaining: 2m 9s
54:	learn: 136.9570899	total: 2m 34s	remaining: 2m 6s
55:	learn: 119.1706178	total: 2m 37s	remaining: 2m 3s
56:	learn: 128.7746874	total: 2m 40s	remaining: 2m 1s
57:	learn: 151.7225275	total: 2m 43s	remaining: 1m 58s
58:	learn: 122.1054599	total: 2m 46s	remaining: 1m 55s
59:	learn: 108.1747022	total: 2m 48s	remaining: 1m 52s
60:	learn: 181.7407008	total: 2m 51s	remaining: 1m 49s
61:	learn: 156.3364489	total: 2m 54s	remaining: 1m 46s
62:	learn: 133.8281872	total: 2m 57s	remaining: 1m 44s
63:	learn: 103.4778304	total: 3m	remaining: 1m 41s
64:	learn: 89.8928007	total: 3m 2s	remaining: 1m 38s
65:	learn: 152.5775698	total: 3m 5s	remaining: 1m 35s
66:	learn: 139.0814236	total: 3m 8s	remaining: 1m 32s
67:	learn: 129.6280340	total: 3m 11s	remaining: 1m 30s
68:	learn: 127.6386635	total: 3m 14s	remaining: 1m 27s
69:	learn: 98.6849365	total: 3m 16s	remaining: 1m 24s
70:	learn: 98.7607154	total: 3m 19s	remaining: 1m 21s
71:	learn: 115.6433045	total: 3m 22s	remaining: 1m 18s
72:	learn: 118.3375625	total: 3m 25s	remaining: 1m 15s
73:	learn: 128.3580173	total: 3m 28s	remaining: 1m 13s
74:	learn: 100.7277246	total: 3m 31s	remaining: 1m 10s
75:	learn: 127.8588919	total: 3m 33s	remaining: 1m 7s
76:	learn: 135.1362509	total: 3m 36s	remaining: 1m 4s
77:	learn: 134.2434358	total: 3m 39s	remaining: 1m 1s
78:	learn: 121.1008131	total: 3m 42s	remaining: 59.1s
79:	learn: 114.3376825	total: 3m 45s	remaining: 56.3s
80:	learn: 110.6201460	total: 3m 48s	remaining: 53.5s
81:	learn: 100.8578425	total: 3m 50s	remaining: 50.6s
82:	learn: 111.1851405	total: 3m 53s	remaining: 47.8s
83:	learn: 103.5908212	total: 3m 56s	remaining: 45s
84:	learn: 103.9389498	total: 3m 59s	remaining: 42.2s
85:	learn: 106.7248996	total: 4m 2s	remaining: 39.4s
86:	learn: 118.8261016	total: 4m 5s	remaining: 36.6s
87:	learn: 109.4252575	total: 4m 7s	remaining: 33.8s
88:	learn: 94.0010108	total: 4m 10s	remaining: 30.9s
89:	learn: 89.6506516	total: 4m 13s	remaining: 28.1s
90:	learn: 123.6613819	total: 4m 16s	remaining: 25.3s
91:	learn: 112.2204298	total: 4m 19s	remaining: 22.5s
92:	learn: 97.8841373	total: 4m 21s	remaining: 19.7s
93:	learn: 108.9219836	total: 4m 24s	remaining: 16.9s
94:	learn: 107.5061509	total: 4m 27s	remaining: 14.1s
95:	learn: 98.2353095	total: 4m 30s	remaining: 11.3s
96:	learn: 96.0087220	total: 4m 33s	remaining: 8.45s
97:	learn: 91.7360796	total: 4m 36s	remaining: 5.63s
98:	learn: 106.1429995	total: 4m 38s	remaining: 2.81s
99:	learn: 105.8996912	total: 4m 41s	remaining: 0us


print(f"Accuracy Score of Ada Boost Classifier is : {acc_cat}")
print(f"Confusion Matrix : \n{conf}")
print(f"Classification Report : \n{clf_report}")

Accuracy Score of Ada Boost Classifier is : 0.9560145647863886
Confusion Matrix : 
[[    0     0   557 ...     0     0     0]
 [ 1426 20535   356 ...     0     0     0]
 [   59   153 65932 ...     0     0     0]
 ...
 [    1   163     0 ...     0     0     0]
 [    0     0     0 ...     0 82055     0]
 [    0     0     0 ...     0     0  4298]]
Classification Report : 
              precision    recall  f1-score   support

           0       0.00      0.00      0.00       559
           1       0.93      0.90      0.91     22870
           2       0.98      1.00      0.99     66144
           3       1.00      1.00      1.00     21149
           4       0.00      0.00      0.00        10
           5       0.93      0.79      0.85      1748
           6       1.00      1.00      1.00     38801
           7       0.74      0.62      0.67      9173
           8       0.99      0.99      0.99     18869
           9       1.00      0.99      1.00       544
          10       1.00      0.72      0.84       661
          11       0.00      0.00      0.00         7
          12       0.36      0.15      0.21      1556
          13       0.00      0.01      0.00       164
          14       0.71      0.29      0.41       272
          15       1.00      0.98      0.99       491
          16       0.96      0.93      0.94     15240
          17       0.99      0.95      0.97     33789
          18       0.00      0.00      0.00         7
          19       0.00      0.00      0.00        26
          21       0.00      0.00      0.00        57
          22       0.86      0.54      0.66      2803
          23       0.00      0.00      0.00         7
          24       0.78      0.93      0.85     21830
          25       1.00      1.00      1.00      1880
          26       0.00      0.00      0.00        14
          27       0.64      0.70      0.67      3261
          28       1.00      1.00      1.00     14425
          29       0.81      0.86      0.84      1255
          30       0.00      0.00      0.00       198
          31       1.00      1.00      1.00     82055
          32       1.00      1.00      1.00      4301

    accuracy                           0.96    364166
   macro avg       0.61      0.57      0.59    364166
weighted avg       0.96      0.96      0.96    364166


etc = ExtraTreesClassifier()
etc.fit(X_train, y_train)

y_pred_etc = etc.predict(X_test)

acc_etc = accuracy_score(y_test, y_pred_etc)
conf = confusion_matrix(y_test, y_pred_etc)
clf_report = classification_report(y_test, y_pred_etc)

print(f"Accuracy Score of Ada Boost Classifier is : {acc_etc}")
print(f"Confusion Matrix : \n{conf}")
print(f"Classification Report : \n{clf_report}")

Accuracy Score of Ada Boost Classifier is : 0.9620337977735428
Confusion Matrix : 
[[  358     2   164 ...     0     2     0]
 [    0 22252   467 ...    38    48     0]
 [    2   113 65913 ...     0    52     0]
 ...
 [    0   153     9 ...     6     2     0]
 [    0    30    76 ...     1 81909     0]
 [    0     0     0 ...     0     0  4086]]
Classification Report : 
              precision    recall  f1-score   support

           0       0.99      0.64      0.78       559
           1       0.98      0.97      0.98     22870
           2       0.99      1.00      0.99     66144
           3       1.00      0.98      0.99     21149
           4       0.17      0.20      0.18        10
           5       0.92      0.93      0.92      1748
           6       0.99      1.00      1.00     38801
           7       0.69      0.63      0.66      9173
           8       1.00      0.99      1.00     18869
           9       0.99      0.88      0.93       544
          10       1.00      0.99      1.00       661
          11       0.00      0.00      0.00         7
          12       0.48      0.43      0.45      1556
          13       0.09      0.04      0.06       164
          14       0.33      0.15      0.21       272
          15       0.99      0.96      0.98       491
          16       1.00      0.97      0.99     15240
          17       0.97      0.98      0.98     33789
          18       0.00      0.00      0.00         7
          19       0.25      0.08      0.12        26
          21       0.25      0.05      0.09        57
          22       0.73      0.63      0.67      2803
          23       0.00      0.00      0.00         7
          24       0.80      0.86      0.83     21830
          25       1.00      0.97      0.98      1880
          26       0.00      0.00      0.00        14
          27       0.66      0.62      0.64      3261
          28       0.99      1.00      0.99     14425
          29       0.86      0.78      0.82      1255
          30       0.11      0.03      0.05       198
          31       0.99      1.00      1.00     82055
          32       0.99      0.95      0.97      4301

    accuracy                           0.96    364166
   macro avg       0.66      0.62      0.63    364166
weighted avg       0.96      0.96      0.96    364166


lgbm = LGBMClassifier(learning_rate = 1)
lgbm.fit(X_train, y_train)

y_pred_lgbm = lgbm.predict(X_test)

acc_lgbm = accuracy_score(y_test, y_pred_lgbm)
conf = confusion_matrix(y_test, y_pred_lgbm)
clf_report = classification_report(y_test, y_pred_lgbm)

print(f"Accuracy Score of Ada Boost Classifier is : {acc_lgbm}")
print(f"Confusion Matrix : \n{conf}")
print(f"Classification Report : \n{clf_report}")

Accuracy Score of Ada Boost Classifier is : 0.1504039366662456
Confusion Matrix : 
[[    0     0   189 ...     0   241     0]
 [    0     0  9290 ...     0 11334     0]
 [    0     0 27810 ...     0 33496     0]
 ...
 [    0     0    96 ...     0    82     0]
 [    0     0 40802 ...     0 25680     0]
 [    0     0  1127 ...     0  2659     0]]
Classification Report : 
              precision    recall  f1-score   support

           0       0.00      0.00      0.00       559
           1       0.00      0.00      0.00     22870
           2       0.18      0.42      0.25     66144
           3       0.00      0.00      0.00     21149
           4       0.00      0.00      0.00        10
           5       0.00      0.00      0.00      1748
           6       0.00      0.00      0.00     38801
           7       0.01      0.00      0.00      9173
           8       0.02      0.05      0.03     18869
           9       0.00      0.00      0.00       544
          10       0.00      0.00      0.00       661
          11       0.00      0.00      0.00         7
          12       0.00      0.00      0.00      1556
          13       0.00      0.00      0.00       164
          14       0.00      0.00      0.00       272
          15       0.00      0.00      0.00       491
          16       0.54      0.00      0.00     15240
          17       0.53      0.01      0.01     33789
          18       0.00      0.00      0.00         7
          19       0.00      0.00      0.00        26
          21       0.00      0.00      0.00        57
          22       0.00      0.00      0.00      2803
          23       0.00      0.00      0.00         7
          24       1.00      0.00      0.00     21830
          25       0.00      0.00      0.00      1880
          26       0.00      0.00      0.00        14
          27       0.01      0.00      0.00      3261
          28       0.46      0.00      0.01     14425
          29       0.00      0.00      0.00      1255
          30       0.00      0.00      0.00       198
          31       0.16      0.31      0.21     82055
          32       0.00      0.00      0.00      4301

    accuracy                           0.15    364166
   macro avg       0.09      0.02      0.02    364166
weighted avg       0.22      0.15      0.10    364166


models = pd.DataFrame({
    'Model' : ['Logistic Regression', 'KNN', 'Decision Tree Classifier', 'Random Forest Classifier','Ada Boost Classifier',
             'Gradient Boosting Classifier', 'XgBoost', 'Cat Boost', 'Extra Trees Classifier', 'LGBM'],
    'Score' : [acc_lr, acc_knn, acc_dtc, acc_rd_clf, acc_ada, acc_gb, acc_xgb, acc_cat, acc_etc, acc_lgbm]
})


models.sort_values(by = 'Score', ascending = False)


px.bar(data_frame = models.sort_values(by = 'Score', ascending = False), 
       x = 'Score', y = 'Model', color = 'Score', template = 'plotly_dark', title = 'Models Comparison')

	Unnamed: 0	ID	Case Number	Date	Block	IUCR	Primary Type	Description	Location Description	Arrest	Domestic	Beat	District	Ward	Community Area	FBI Code	X Coordinate	Y Coordinate	Year	Updated On	Latitude	Longitude	Location
0	3	10508693	HZ250496	05/03/2016 11:40:00 PM	013XX S SAWYER AVE	0486	BATTERY	DOMESTIC BATTERY SIMPLE	APARTMENT	True	True	1022	10.0	24.0	29.0	08B	1154907.0	1893681.0	2016	05/10/2016 03:56:50 PM	41.864073	-87.706819	(41.864073157, -87.706818608)
1	89	10508695	HZ250409	05/03/2016 09:40:00 PM	061XX S DREXEL AVE	0486	BATTERY	DOMESTIC BATTERY SIMPLE	RESIDENCE	False	True	313	3.0	20.0	42.0	08B	1183066.0	1864330.0	2016	05/10/2016 03:56:50 PM	41.782922	-87.604363	(41.782921527, -87.60436317)
2	197	10508697	HZ250503	05/03/2016 11:31:00 PM	053XX W CHICAGO AVE	0470	PUBLIC PEACE VIOLATION	RECKLESS CONDUCT	STREET	False	False	1524	15.0	37.0	25.0	24	1140789.0	1904819.0	2016	05/10/2016 03:56:50 PM	41.894908	-87.758372	(41.894908283, -87.758371958)
3	673	10508698	HZ250424	05/03/2016 10:10:00 PM	049XX W FULTON ST	0460	BATTERY	SIMPLE	SIDEWALK	False	False	1532	15.0	28.0	25.0	08B	1143223.0	1901475.0	2016	05/10/2016 03:56:50 PM	41.885687	-87.749516	(41.885686845, -87.749515983)
4	911	10508699	HZ250455	05/03/2016 10:00:00 PM	003XX N LOTUS AVE	0820	THEFT	$500 AND UNDER	RESIDENCE	False	True	1523	15.0	28.0	25.0	06	1139890.0	1901675.0	2016	05/10/2016 03:56:50 PM	41.886297	-87.761751	(41.886297242, -87.761750709)

	Unnamed: 0	ID	Beat	District	Ward	Community Area	X Coordinate	Y Coordinate	Year	Latitude	Longitude
count	1.456714e+06	1.456714e+06	1.456714e+06	1.456713e+06	1.456700e+06	1.456674e+06	1.419631e+06	1.419631e+06	1.456714e+06	1.419631e+06	1.419631e+06
mean	3.308606e+06	9.597550e+06	1.150644e+03	1.125920e+01	2.287027e+01	3.745632e+01	1.164398e+06	1.885523e+06	2.013897e+03	4.184147e+01	-8.767224e+01
std	1.235350e+06	8.083505e+05	6.916466e+02	6.904691e+00	1.380589e+01	2.144029e+01	1.850835e+04	3.424775e+04	1.449584e+00	9.430126e-02	6.661726e-02
min	3.000000e+00	2.022400e+04	1.110000e+02	1.000000e+00	1.000000e+00	0.000000e+00	0.000000e+00	0.000000e+00	2.012000e+03	3.661945e+01	-9.168657e+01
25%	2.698636e+06	9.002709e+06	6.130000e+02	6.000000e+00	1.000000e+01	2.300000e+01	1.152544e+06	1.858762e+06	2.013000e+03	4.176787e+01	-8.771528e+01
50%	3.063654e+06	9.605776e+06	1.024000e+03	1.000000e+01	2.300000e+01	3.200000e+01	1.166021e+06	1.891502e+06	2.014000e+03	4.185797e+01	-8.766613e+01
75%	3.428849e+06	1.022577e+07	1.711000e+03	1.700000e+01	3.400000e+01	5.600000e+01	1.176363e+06	1.908713e+06	2.015000e+03	4.190529e+01	-8.762813e+01
max	6.253474e+06	1.082788e+07	2.535000e+03	3.100000e+01	5.000000e+01	7.700000e+01	1.205119e+06	1.951573e+06	2.017000e+03	4.202271e+01	-8.752453e+01

	Null Values	Percentage Null Values
Unnamed: 0	0	0.000000
ID	0	0.000000
Case Number	1	0.000069
Date	0	0.000000
Block	0	0.000000
IUCR	0	0.000000
Primary Type	0	0.000000
Description	0	0.000000
Location Description	1658	0.113818
Arrest	0	0.000000
Domestic	0	0.000000
Beat	0	0.000000
District	1	0.000069
Ward	14	0.000961
Community Area	40	0.002746
FBI Code	0	0.000000
X Coordinate	37083	2.545661
Y Coordinate	37083	2.545661
Year	0	0.000000
Updated On	0	0.000000
Latitude	37083	2.545661
Longitude	37083	2.545661
Location	37083	2.545661

	Unnamed: 0	ID	Case Number	Date	Block	IUCR	Primary Type	Description	Location Description	Arrest	Domestic	Beat	District	Ward	Community Area	FBI Code	X Coordinate	Y Coordinate	Year	Updated On	Latitude	Longitude	Location
0	3	10508693	HZ250496	05/03/2016 11:40:00 PM	013XX S SAWYER AVE	0486	BATTERY	DOMESTIC BATTERY SIMPLE	APARTMENT	True	True	1022	10.0	24.0	29.0	08B	1154907.0	1893681.0	2016	05/10/2016 03:56:50 PM	41.864073	-87.706819	(41.864073157, -87.706818608)
1	89	10508695	HZ250409	05/03/2016 09:40:00 PM	061XX S DREXEL AVE	0486	BATTERY	DOMESTIC BATTERY SIMPLE	RESIDENCE	False	True	313	3.0	20.0	42.0	08B	1183066.0	1864330.0	2016	05/10/2016 03:56:50 PM	41.782922	-87.604363	(41.782921527, -87.60436317)
2	197	10508697	HZ250503	05/03/2016 11:31:00 PM	053XX W CHICAGO AVE	0470	PUBLIC PEACE VIOLATION	RECKLESS CONDUCT	STREET	False	False	1524	15.0	37.0	25.0	24	1140789.0	1904819.0	2016	05/10/2016 03:56:50 PM	41.894908	-87.758372	(41.894908283, -87.758371958)
3	673	10508698	HZ250424	05/03/2016 10:10:00 PM	049XX W FULTON ST	0460	BATTERY	SIMPLE	SIDEWALK	False	False	1532	15.0	28.0	25.0	08B	1143223.0	1901475.0	2016	05/10/2016 03:56:50 PM	41.885687	-87.749516	(41.885686845, -87.749515983)
4	911	10508699	HZ250455	05/03/2016 10:00:00 PM	003XX N LOTUS AVE	0820	THEFT	$500 AND UNDER	RESIDENCE	False	True	1523	15.0	28.0	25.0	06	1139890.0	1901675.0	2016	05/10/2016 03:56:50 PM	41.886297	-87.761751	(41.886297242, -87.761750709)
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1456709	6250330	10508679	HZ250507	05/03/2016 11:33:00 PM	026XX W 23RD PL	0486	BATTERY	DOMESTIC BATTERY SIMPLE	APARTMENT	True	True	1034	10.0	28.0	30.0	08B	1159105.0	1888300.0	2016	05/10/2016 03:56:50 PM	41.849222	-87.691556	(41.849222028, -87.69155551)
1456710	6251089	10508680	HZ250491	05/03/2016 11:30:00 PM	073XX S HARVARD AVE	1310	CRIMINAL DAMAGE	TO PROPERTY	APARTMENT	True	True	731	7.0	17.0	69.0	14	1175230.0	1856183.0	2016	05/10/2016 03:56:50 PM	41.760744	-87.633335	(41.760743949, -87.63333531)
1456711	6251349	10508681	HZ250479	05/03/2016 12:15:00 AM	024XX W 63RD ST	041A	BATTERY	AGGRAVATED: HANDGUN	SIDEWALK	False	False	825	8.0	15.0	66.0	04B	1161027.0	1862810.0	2016	05/10/2016 03:56:50 PM	41.779235	-87.685207	(41.779234743, -87.685207125)
1456712	6253257	10508690	HZ250370	05/03/2016 09:07:00 PM	082XX S EXCHANGE AVE	0486	BATTERY	DOMESTIC BATTERY SIMPLE	SIDEWALK	False	True	423	4.0	7.0	46.0	08B	1197261.0	1850727.0	2016	05/10/2016 03:56:50 PM	41.745252	-87.552773	(41.745251975, -87.552773464)
1456713	6253474	10508692	HZ250517	05/03/2016 11:38:00 PM	001XX E 75TH ST	5007	OTHER OFFENSE	OTHER WEAPONS VIOLATION	PARKING LOT/GARAGE(NON.RESID.)	True	False	323	3.0	6.0	69.0	26	1178696.0	1855324.0	2016	05/10/2016 03:56:50 PM	41.758309	-87.620658	(41.75830866, -87.620658418)

	Unnamed: 0.1	Unnamed: 0	ID	Case Number	Date	Block	Primary Type	Location Description	Arrest	Domestic	Beat	District	Ward	Community Area	FBI Code	X Coordinate	Y Coordinate	Year	Updated On	Latitude	Longitude	Location	poverty	median_house_income	black	naturecitizenship	health_insurance	hispanic_latino	noncitizenship	owner_occupied	education
0	0	3	10508693	1259878	193027	6516	2	18	True	True	1022	10.0	24.0	29.0	10	1154907.0	1893681.0	2016	305	41.864073	-87.706819	192925	0.406	27397	0.873900	0.011372	0.889	0.088320	0.021061	0.245	0.1237
1	1	48110	10448396	1224287	113700	9284	3	18	False	False	1024	10.0	24.0	29.0	6	1153729.0	1890276.0	2016	306	41.854753	-87.711234	184458	0.406	27397	0.873900	0.011372	0.889	0.088320	0.021061	0.245	0.1237
2	2	52366	10495378	1251596	175514	7416	32	135	True	False	1021	10.0	24.0	29.0	17	1154286.0	1892167.0	2016	306	41.859931	-87.709139	189929	0.406	27397	0.873900	0.011372	0.889	0.088320	0.021061	0.245	0.1237
3	3	57943	20859	428099	188612	9233	10	16	True	False	1024	10.0	24.0	29.0	0	1153059.0	1890107.0	2013	306	41.854302	-87.713697	183911	0.470	24144	0.890039	0.008618	0.828	0.070019	0.025740	0.250	0.1100
4	4	63024	10508736	1259927	194418	15986	1	18	True	True	1133	11.0	24.0	29.0	4	1152965.0	1894830.0	2016	307	41.867265	-87.713917	196143	0.406	27397	0.873900	0.011372	0.889	0.088320	0.021061	0.245	0.1237

	Block	Primary Type	Location Description	Arrest	Domestic	Beat	District	Ward	Community Area	FBI Code	Y Coordinate	Year	Updated On	Location	poverty	median_house_income	black	naturecitizenship	health_insurance	hispanic_latino	noncitizenship	education
0	0.198944	2	0.126761	True	True	0.375825	0.322581	0.48	0.368421	0.40	0.970336	0.8	0.318372	0.523860	0.607477	0.110899	0.873688	0.028431	0.726994	0.095362	0.058532	0.104457
1	0.283455	3	0.126761	False	False	0.376650	0.322581	0.48	0.368421	0.24	0.968591	0.8	0.319415	0.500869	0.607477	0.110899	0.873688	0.028431	0.726994	0.095362	0.058532	0.104457
2	0.226422	32	0.950704	True	False	0.375413	0.322581	0.48	0.368421	0.68	0.969560	0.8	0.319415	0.515725	0.607477	0.110899	0.873688	0.028431	0.726994	0.095362	0.058532	0.104457
3	0.281898	10	0.112676	True	False	0.376650	0.322581	0.48	0.368421	0.00	0.968504	0.2	0.319415	0.499384	0.707165	0.081797	0.889854	0.020111	0.539877	0.075602	0.071535	0.087400
4	0.488077	1	0.126761	True	True	0.421617	0.354839	0.48	0.368421	0.16	0.970924	0.8	0.320459	0.532598	0.607477	0.110899	0.873688	0.028431	0.726994	0.095362	0.058532	0.104457
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1456656	0.937258	2	0.859155	False	False	0.867162	0.709677	0.38	0.934211	0.40	0.000000	1.0	0.086639	1.000000	0.052960	0.756989	0.341171	0.070237	0.960123	0.053356	0.033000	0.635209
1456657	0.903062	8	0.788732	False	False	0.870462	0.709677	0.38	0.934211	0.52	0.000000	1.0	0.090814	1.000000	0.052960	0.756989	0.341171	0.070237	0.960123	0.053356	0.033000	0.635209
1456658	0.954081	31	0.901408	False	False	0.866749	0.709677	0.38	0.934211	0.28	0.000000	1.0	0.090814	1.000000	0.052960	0.756989	0.341171	0.070237	0.960123	0.053356	0.033000	0.635209
1456659	0.937410	8	0.788732	False	False	0.866337	0.709677	0.38	0.934211	0.52	0.000000	1.0	0.090814	1.000000	0.052960	0.756989	0.341171	0.070237	0.960123	0.053356	0.033000	0.635209
1456660	0.199463	8	0.161972	False	False	0.866749	0.709677	0.42	0.934211	0.52	0.000000	1.0	0.090814	1.000000	0.052960	0.756989	0.341171	0.070237	0.960123	0.053356	0.033000	0.635209

	Model	Score
6	XgBoost	0.975687
4	Ada Boost Classifier	0.971884
3	Random Forest Classifier	0.966746
2	Decision Tree Classifier	0.964813
8	Extra Trees Classifier	0.962034
7	Cat Boost	0.956015
5	Gradient Boosting Classifier	0.912397
1	KNN	0.818846
0	Logistic Regression	0.703097
9	LGBM	0.150404

Note: Trainning for these 10 models may take more than 5 hours;¶